Pradana, Dandy Aurrellio (2025) SENTIMENT ANALYSIS USING NAÏVE BAYES CLASSIFIER ALGORITHM ON COMPASS SHOE PRODUCTS. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411368_Dandy Aurrellio Pradana_Abstrak.pdf Download (11kB) |
Abstract
This study analyzes customer sentiment toward Compass shoes on Tokopedia using the Multinomial Naïve Bayes algorithm. A total of 1,521 product reviews were collected through web scraping and processed through several stages, including data cleaning, normalization, and sentiment labelling. The developed model achieved an accuracy of 92.31%, with strong precision and recall scores for both negative (0.88 and 0.98) and positive (0.98 and 0.86) sentiments. The use of Term Frequency-Inverse Document Frequency (TF-IDF) for feature extraction and Synthetic Minority Over-sampling Technique (SMOTE) for class balancing proved to be effective. Sentiment distribution was further clarified through visualizations such as word clouds for positive and negative reviews and a confidence score table. The findings of this study can be utilized to improve product quality and customer service by leveraging consumer feedback identified through sentiment analysis.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 16 Jul 2025 01:47 |
| Last Modified: | 16 Jul 2025 01:47 |
| URI: | http://eprints.uty.ac.id/id/eprint/18151 |
Actions (login required)
 |
View Item |
